Laya on Axera AX650 and AX8850 edge NPUs, under 70 ms
AXERA-TECH's conversion of all three Laya checkpoints for its edge AI chips, reported at latency under 70 ms per decision on AX650/AX8850.
README not available at build time.
AXERA-TECH's conversion of all three Laya checkpoints for its edge AI chips, reported at latency under 70 ms per decision on AX650/AX8850.
README not available at build time.
介绍比Jev快50倍,在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇! https://t.co/31KGUiNunb
@mizorewww · Tools & apps · free, local · 60 decisions/s
@mizorewww
X post
Tools & apps
free, local
60 decisions/s
MCP server plus HTTP sidecar: token-budget preflight that reports what would be cut, a persisted calibration store, structured errors, and a noul fix (P(true) 0.5 → 1.0).
@PerryLink · Tools & apps · free, local
@PerryLink
GitHub
Tools & apps
free, local
-
Local 15x15 Gomoku on Apple Silicon. Rules in Python, board in the browser, every AI move one real Laya choice over up to six candidates, probabilities shown. No Gomoku training.
smile-magic · Tools & apps · free, local
smile-magic
GitHub
Tools & apps
free, local
-
From the Prompt Engineer 48 video. Both models get the same input and typed questions; only the model differs. Laya needs no key.
@PromptEngineer48 · Tools & apps · free, local (Laya)
@PromptEngineer48
GitHub
Tools & apps
free, local (Laya)
-